Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3198 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.5324. Min Act: -0.0000

Data Index: 704637 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.5172. Min Act: -0.0000

Data Index: 549965 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1057514 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4780. Min Act: -0.0000

Data Index: 786338 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4347. Min Act: -0.0000

Data Index: 77213 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4212. Min Act: -0.0000

Data Index: 320037 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1161135 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1823418 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3877. Min Act: -0.0000

Data Index: 741928 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3929. Min Act: -0.0000

Data Index: 582632 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4570. Min Act: -0.0000

Data Index: 319267 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3703. Min Act: -0.0000

Data Index: 557489 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3346. Min Act: -0.0000

Data Index: 964020 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1915585 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1470832 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.4174. Min Act: -0.0000

Data Index: 449569 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3796. Min Act: -0.0000

Data Index: 75691 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3777. Min Act: -0.0000

Data Index: 920548 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3262. Min Act: -0.0000

Data Index: 842559 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.5324. Min Range: -0.5324

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1255177 (The Pile)

Max Activating Token Index: 792